{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01558846453624318,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005196154845414394,
      "eval_loss": NaN,
      "eval_runtime": 27.6628,
      "eval_samples_per_second": 29.317,
      "eval_steps_per_second": 14.677,
      "step": 1
    },
    {
      "epoch": 0.001558846453624318,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.003117692907248636,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.004156923876331515,
      "eval_loss": NaN,
      "eval_runtime": 26.5573,
      "eval_samples_per_second": 30.538,
      "eval_steps_per_second": 15.288,
      "step": 8
    },
    {
      "epoch": 0.004676539360872954,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.006235385814497272,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00779423226812159,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00831384775266303,
      "eval_loss": NaN,
      "eval_runtime": 26.5761,
      "eval_samples_per_second": 30.516,
      "eval_steps_per_second": 15.277,
      "step": 16
    },
    {
      "epoch": 0.009353078721745909,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.010911925175370226,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.012470771628994544,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.012470771628994544,
      "eval_loss": NaN,
      "eval_runtime": 26.5447,
      "eval_samples_per_second": 30.552,
      "eval_steps_per_second": 15.295,
      "step": 24
    },
    {
      "epoch": 0.014029618082618862,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.01558846453624318,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 492644613488640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}